Distributed reinforcement learning

By Gerhard Weiss. 1995

Subfields: Reinforcement Learning, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Peter Stone
2. Sergey Levine
3. Pieter Abbeel
4. J. Urgen Schmidhuber
5. Jan Peters
6. Manuela M. Veloso
7. Shimon Whiteson
8. Matthew E. Taylor

In ML Systems & Hardware

1. Peter Stone
2. Klaus-Jürgen Diepold
3. Andrew W. Moore
4. Manuela M. Veloso
5. Sven Gronauer
6. Martin A. Riedmiller
7. Sean Luke
8. Liviu Panait

Citations in the corpus

• Multi-agent deep reinforcement learning: a survey (2021, background): “Associating rewards to agents is known as the credit assignment problem (Chang et al. 2004; Weiß 1995; Wolpert and Tumer 1999).”
• Towards collaborative and adversarial learning: a case study in robotic soccer (1998, background): “As described by Weiß, it is “learning that is done by several agents and that becomes possible only because several agents are present” (Weiß, 1995).”
• Distributed Value Functions (1999, background): “Weiss proposes a \bucket brigade" scheme for credit assignment among cooperating reinforcement learning agents[17].”
• Multirobot systems: a classification focused on coordination (2004, background): “In fact, due to the inherent complexity of MRS, Machine Learning is an issue of great interest [114], [95] and many existing learning techniques can be directly applied in a multi-agent scenario, by delimiting a part of the domain that involves only a single agent, as described by Weiss [43].”